Wenhao Yu

About Me

My primary research interest lies in post-training large language models (LLMs) for reasoning and agentic capabilities. My current focus is building self-improving LLMs that can continuously learn from interaction, feedback, and experience. To support this goal, I have extensively studied and applied reinforcement learning (RL) for post-training, reasoning, and agentic behaviors in large-scale models.

I earned my Ph.D. in Computer Science and Engineering from University of Notre Dame in 2023, advised by Prof. Meng Jiang . My research during Ph.D. was generously supported by the Bloomberg Ph.D Fellowship . I also enjoyed amazing internship experiences at Microsoft Research, AI2, and Bloomberg.

What's New

Check my latest post on X (Twitter)
Jan 2026 Four papers have been accepted at ICLR 2026, covering topics of self-improving LLMs and parallel reasoning.
Aug 2025 One paper has been accepted at EMNLP 2025 on self-evolving agent.

Selected Publications

For a full list of publications, please refer to my Google Scholar page .

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu

[ICLR 2026] International Conference on Learning Representations

pdf code

Parallel-r1: Towards parallel thinking via reinforcement learning

Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu

[ICLR 2026] International Conference on Learning Representations

pdf code

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

TZhaowei Wang, Wenhao Yu, Xiyu Ren, Jipeng Zhang, Yu Zhao, Rohit Saxena, Liang Cheng, Ginny Wong, Simon See, Pasquale Minervini, Yangqiu Song, Mark Steedman

[NeurIPS 2025] Conference on Neural Information Processing Systems

pdf code

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, Dong Yu

[ICLR 2025] International Conference on Learning Representations

pdf code

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

Siru Ouyang, Wenhao Yu, Kaixin Ma, Zilin Xiao, Zhihan Zhang, Mengzhao Jia, Jiawei Han, Hongming Zhang, Dong Yu

[ICLR 2025] International Conference on Learning Representations

pdf code

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu

[ACL 2024] 2024 Annual Conference of Association for Computational Linguistics

pdf code

Internship with Me

I am actively seeking highly motivated interns who share my research interests. Kindly reach out to me through email with your resume. I’ve been fortunate to mentor and work alongside many talented students:

Chengsong Huang (2025), WUSTL, advised by Prof. Jiaxin Huang. Topic: Self-improving LLM [R-Zero]
Shangbin Feng (2025), UW at Seattle, advised by Prof. Yulia Tsvetkov. Topic: Multi-Agent [SwitcherLM]
Zongxia Li (2025), UMD, advised by Prof. Jordan Boyd-Graber. Topic: Self-improving LLM [Vision-SR1]
Siru Ouyang (2024), UIUC, advised by Prof. Jiawei Han. Topic: LLM agent [RepoGraph]
Mengzhao Jia (2024), UND, advised by Prof. Meng Jiang. Topic: Multi-modal [Leopard]
Tong Chen (2023), UW at Seattle, advised by Prof. Luke Zettlemoyer Topic: RAG [Dense X Retrieval]